Visible-Infrared Person Re-Identification via Patch-Mixed Cross-Modality Learning
This work solves the modality gap issue in cross-modality person re-identification for surveillance applications, representing an incremental improvement over existing methods.
The paper tackles the problem of visible-infrared person re-identification by addressing modality discrepancy and introduces a Patch-Mixed Cross-Modality framework that splits and stitches patches from two modalities to learn semantic correspondence, achieving new state-of-the-art performance on two datasets.
Visible-infrared person re-identification (VI-ReID) aims to retrieve images of the same pedestrian from different modalities, where the challenges lie in the significant modality discrepancy. To alleviate the modality gap, recent methods generate intermediate images by GANs, grayscaling, or mixup strategies. However, these methods could introduce extra data distribution, and the semantic correspondence between the two modalities is not well learned. In this paper, we propose a Patch-Mixed Cross-Modality framework (PMCM), where two images of the same person from two modalities are split into patches and stitched into a new one for model learning. A part-alignment loss is introduced to regularize representation learning, and a patch-mixed modality learning loss is proposed to align between the modalities. In this way, the model learns to recognize a person through patches of different styles, thereby the modality semantic correspondence can be inferred. In addition, with the flexible image generation strategy, the patch-mixed images freely adjust the ratio of different modality patches, which could further alleviate the modality imbalance problem. On two VI-ReID datasets, we report new state-of-the-art performance with the proposed method.